Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hanhuark/mechanical-engineering-research-skill --skill thermal-fluid-analysisgit clone --depth 1 https://github.com/hanhuark/mechanical-engineering-research-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hanhuark/mechanical-engineering-research-skill/thermal-fluid-analysis)<a href="https://agentmods.dev/skills/hanhuark/mechanical-engineering-research-skill/thermal-fluid-analysis"><img src="https://agentmods.dev/badge/skills/hanhuark/mechanical-engineering-research-skill/thermal-fluid-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hanhuark/mechanical-engineering-research-skill/thermal-fluid-analysis"><img src="https://agentmods.dev/badge/skills/hanhuark/mechanical-engineering-research-skill/thermal-fluid-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00496 |
| Opus 5.5 | $0.00022 | $0.00198 |
| Sonnet 5.5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
thermal-fluid-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thermal-Fluid Analysis
Purpose
Develop decision-ready thermal-fluid analysis without separating numerical output from physical meaning. State what is measured, simulated, derived, assumed, or inferred; retain units, sign conventions, property states, system boundaries, and applicability limits.
Analysis Workflow
- Define the system: geometry, working fluid, operating regime, boundary conditions, performance metrics, and constraints.
- Establish the physical model: governing balances, material properties and their evaluation state, dimensionless groups, competing mechanisms, and expected limiting behavior.
- Select evidence: standards, handbooks, peer-reviewed work, calibrated measurements, validated CFD, or correlations inside their stated range.
- Test credibility: dimensional consistency, conservation, order of magnitude, limiting cases, uncertainty/sensitivity, and an independent analytical or empirical check where possible.
- Conclude by mechanism and tradeoff: performance, pressure drop or pumping power, manufacturability, reliability, cost, safety, scaling, and residual risk.
Experiments
Report the facility and specimen geometry, instrumentation, calibration, sampling, procedure, data reduction, heat-loss treatment, repeatability, uncertainty propagation, and exclusions. Distinguish sensor uncertainty from run-to-run variability. Do not call a preliminary demonstration validation without a stated comparison target.
CFD And Modeling
List all assumptions before presenting results and justify each one. State the domain, mesh and mesh-independence evidence, models, wall treatment, property models, boundary and initial conditions, solver/convergence criteria, time step where applicable, and validation data. Treat a converged solution as numerical evidence, not experimental proof.
Results Discussion
For each important figure, move through: what is plotted; what changes; the physical explanation; and comparison with literature, theory, or an independent data source. Do not merely restate a trend. Explain the regime, competing mechanisms, and the conditions under which the conclusion might fail.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 35 lines · 56 tokens per session scan A d9883d0f6ffa
thermal-fluid-analysis is a skill published in the GitHub repository hanhuark/mechanical-engineering-research-skill (22 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 496 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
deep-research
Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
complexa-sweep
Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product hyperparameter scans, sweeper YAML authoring, configuration comparisons, ablations, tuning, success-rate ranking, or Pareto searches over quality and wall-clock cost. Do…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
parabricks
Plan NVIDIA Parabricks pbrun commands, translate CPU options and check runtime readiness. Use for individual tools, including planning-only questions.
complexa-evaluate-pdbs
Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, ipLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs.…